Large Language Models

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models ICML 2025 Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions ICML 2025 SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs ICML 2025 Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations NAACL 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding ICML 2025 Speculative Decoding for Multi-Sample Inference EMNLP 2025 Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation ICML 2025 Speculative Safety-Aware Decoding EMNLP 2025 Speculative Sampling via Exponential Races ACL 2025 Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025 Speech Annotation for A: Accuracy, Access, and Application Interspeech 2025 Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models Interspeech 2025 SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models ACL 2025 Speechless: Speech Instruction Training Without Speech for Low Resource Languages Interspeech 2025 Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages Interspeech 2025 Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing ACL 2025 SPEX: Scaling Feature Interaction Explanations for LLMs ICML 2025 SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning EMNLP 2025 sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting ACL 2025 SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment ACL 2025 SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025 SplatTalk: 3D VQA with Gaussian Splatting ICCV 2025 Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs EMNLP 2025 Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models ICML 2025